© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 1059
    Prev
    Next
    INDEX
    Explanations

    mentions of students, such as "Student leaders" or "Black Student Organization"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "student" in various contexts related to a campus setting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bably
    -0.69
     horr
    -0.68
     Bots
    -0.64
    ality
    -0.64
     brisk
    -0.61
    UTERS
    -0.61
     heaviest
    -0.61
    doors
    -0.61
     gland
    -0.60
     glands
    -0.59
    POSITIVE LOGITS
    Student
    0.98
    student
    0.97
    holder
    0.94
    Students
    0.91
     Loan
    0.88
     Student
    0.86
     Gohan
    0.82
     student
    0.82
     Students
    0.80
    uates
    0.80
    Activations Density 0.018%

    No Known Activations